ClawHub
Back to skill

Security audit

Obsidian Cli

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Obsidian CLI helper whose note-management and developer-debugging powers are expected for its purpose, but users should treat write and JavaScript commands carefully.

Install this only if you want an agent to operate your Obsidian vault through the obsidian CLI. Prefer read-only commands for ordinary note lookups, and require explicit review before commands that modify notes, reload plugins, take screenshots, inspect the DOM, or run JavaScript in Obsidian.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation description is broad enough to match many ordinary note-management requests, but this skill exposes powerful capabilities including file modification, plugin reloading, DOM inspection, screenshots, and JavaScript execution. Over-broad routing increases the chance the agent invokes a high-privilege skill in situations where a narrower, safer skill or a confirmation step would be more appropriate.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill advertises and documents commands that can modify vault contents and execute JavaScript in the Obsidian app context, but it provides no safety guidance, permission boundaries, or warnings about these high-risk operations. In this context, missing guardrails are especially dangerous because the same skill combines routine note operations with developer features that can inspect application state, capture data, and run arbitrary code against the user's vault environment.

Static analysis

No suspicious patterns detected.